FAILED: patch "[PATCH] KVM: VMX: Wrap all accesses to IA32_DEBUGCTL with" failed to apply to 6.6-stable tree
The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to stable@vger.kernel.org.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 7d0cce6cbe71af6e9c1831bff101a2b9c249c4a2 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to 'stable@vger.kernel.org' --in-reply-to '2025081214-bonanza-germproof-173f@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 7d0cce6cbe71af6e9c1831bff101a2b9c249c4a2 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky mlevitsk@redhat.com Date: Tue, 10 Jun 2025 16:20:09 -0700 Subject: [PATCH] KVM: VMX: Wrap all accesses to IA32_DEBUGCTL with getter/setter APIs
Introduce vmx_guest_debugctl_{read,write}() to handle all accesses to vmcs.GUEST_IA32_DEBUGCTL. This will allow stuffing FREEZE_IN_SMM into GUEST_IA32_DEBUGCTL based on the host setting without bleeding the state into the guest, and without needing to copy+paste the FREEZE_IN_SMM logic into every patch that accesses GUEST_IA32_DEBUGCTL.
No functional change intended.
Cc: stable@vger.kernel.org Signed-off-by: Maxim Levitsky mlevitsk@redhat.com [sean: massage changelog, make inline, use in all prepare_vmcs02() cases] Reviewed-by: Dapeng Mi dapeng1.mi@linux.intel.com Link: https://lore.kernel.org/r/20250610232010.162191-8-seanjc@google.com Signed-off-by: Sean Christopherson seanjc@google.com
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 1b8b0642fc2d..ef20184b8b11 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2663,11 +2663,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (vmx->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) { kvm_set_dr(vcpu, 7, vmcs12->guest_dr7); - vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl & - vmx_get_supported_debugctl(vcpu, false)); + vmx_guest_debugctl_write(vcpu, vmcs12->guest_ia32_debugctl & + vmx_get_supported_debugctl(vcpu, false)); } else { kvm_set_dr(vcpu, 7, vcpu->arch.dr7); - vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.pre_vmenter_debugctl); + vmx_guest_debugctl_write(vcpu, vmx->nested.pre_vmenter_debugctl); } if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) @@ -3532,7 +3532,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
if (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) - vmx->nested.pre_vmenter_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); + vmx->nested.pre_vmenter_debugctl = vmx_guest_debugctl_read(); if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) @@ -4806,7 +4806,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, __vmx_set_segment(vcpu, &seg, VCPU_SREG_LDTR);
kvm_set_dr(vcpu, 7, 0x400); - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); + vmx_guest_debugctl_write(vcpu, 0);
if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr, vmcs12->vm_exit_msr_load_count)) diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index bbf4509f32d0..0b173602821b 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -653,11 +653,11 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu) */ static void intel_pmu_legacy_freezing_lbrs_on_pmi(struct kvm_vcpu *vcpu) { - u64 data = vmcs_read64(GUEST_IA32_DEBUGCTL); + u64 data = vmx_guest_debugctl_read();
if (data & DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) { data &= ~DEBUGCTLMSR_LBR; - vmcs_write64(GUEST_IA32_DEBUGCTL, data); + vmx_guest_debugctl_write(vcpu, data); } }
@@ -730,7 +730,7 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu)
if (!lbr_desc->event) { vmx_disable_lbr_msrs_passthrough(vcpu); - if (vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR) + if (vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR) goto warn; if (test_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use)) goto warn; @@ -752,7 +752,7 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu)
static void intel_pmu_cleanup(struct kvm_vcpu *vcpu) { - if (!(vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR)) + if (!(vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR)) intel_pmu_release_guest_lbr_event(vcpu); }
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 6a8b78e954cd..a77d325fe78b 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2149,7 +2149,7 @@ int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vmx->pt_desc.guest.addr_a[index / 2]; break; case MSR_IA32_DEBUGCTLMSR: - msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL); + msr_info->data = vmx_guest_debugctl_read(); break; default: find_uret_msr: @@ -2283,7 +2283,8 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) VM_EXIT_SAVE_DEBUG_CONTROLS) get_vmcs12(vcpu)->guest_ia32_debugctl = data;
- vmcs_write64(GUEST_IA32_DEBUGCTL, data); + vmx_guest_debugctl_write(vcpu, data); + if (intel_pmu_lbr_is_enabled(vcpu) && !to_vmx(vcpu)->lbr_desc.event && (data & DEBUGCTLMSR_LBR)) intel_pmu_create_guest_lbr_event(vcpu); @@ -4798,7 +4799,8 @@ static void init_vmcs(struct vcpu_vmx *vmx) vmcs_write32(GUEST_SYSENTER_CS, 0); vmcs_writel(GUEST_SYSENTER_ESP, 0); vmcs_writel(GUEST_SYSENTER_EIP, 0); - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); + + vmx_guest_debugctl_write(&vmx->vcpu, 0);
if (cpu_has_vmx_tpr_shadow()) { vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 392e66c7e5fe..c20a4185d10a 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -417,6 +417,16 @@ void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu); u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated); bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated);
+static inline void vmx_guest_debugctl_write(struct kvm_vcpu *vcpu, u64 val) +{ + vmcs_write64(GUEST_IA32_DEBUGCTL, val); +} + +static inline u64 vmx_guest_debugctl_read(void) +{ + return vmcs_read64(GUEST_IA32_DEBUGCTL); +} + /* * Note, early Intel manuals have the write-low and read-high bitmap offsets * the wrong way round. The bitmaps control MSRs 0x00000000-0x00001fff and
From: Sean Christopherson seanjc@google.com
[ Upstream commit 8a4351ac302cd8c19729ba2636acfd0467c22ae8 ]
Move VMX's logic to check DEBUGCTL values into a standalone helper so that the code can be used by nested VM-Enter to apply the same logic to the value being loaded from vmcs12.
KVM needs to explicitly check vmcs12->guest_ia32_debugctl on nested VM-Enter, as hardware may support features that KVM does not, i.e. relying on hardware to detect invalid guest state will result in false negatives. Unfortunately, that means applying KVM's funky suppression of BTF and LBR to vmcs12 so as not to break existing guests.
No functional change intended.
Reviewed-by: Dapeng Mi dapeng1.mi@linux.intel.com Link: https://lore.kernel.org/r/20250610232010.162191-6-seanjc@google.com Signed-off-by: Sean Christopherson seanjc@google.com Stable-dep-of: 7d0cce6cbe71 ("KVM: VMX: Wrap all accesses to IA32_DEBUGCTL with getter/setter APIs") Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/vmx/vmx.c | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index e53620e18925..48a72ad8a28f 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2168,6 +2168,19 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated return debugctl; }
+static bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, + bool host_initiated) +{ + u64 invalid; + + invalid = data & ~vmx_get_supported_debugctl(vcpu, host_initiated); + if (invalid & (DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR)) { + kvm_pr_unimpl_wrmsr(vcpu, MSR_IA32_DEBUGCTLMSR, data); + invalid &= ~(DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR); + } + return !invalid; +} + /* * Writes msr value into the appropriate "register". * Returns 0 on success, non-0 otherwise. @@ -2236,19 +2249,12 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } vmcs_writel(GUEST_SYSENTER_ESP, data); break; - case MSR_IA32_DEBUGCTLMSR: { - u64 invalid; - - invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated); - if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) { - kvm_pr_unimpl_wrmsr(vcpu, msr_index, data); - data &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); - invalid &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); - } - - if (invalid) + case MSR_IA32_DEBUGCTLMSR: + if (!vmx_is_valid_debugctl(vcpu, data, msr_info->host_initiated)) return 1;
+ data &= vmx_get_supported_debugctl(vcpu, msr_info->host_initiated); + if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) get_vmcs12(vcpu)->guest_ia32_debugctl = data; @@ -2258,7 +2264,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) (data & DEBUGCTLMSR_LBR)) intel_pmu_create_guest_lbr_event(vcpu); return 0; - } case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported() || (!msr_info->host_initiated &&
From: Maxim Levitsky mlevitsk@redhat.com
[ Upstream commit 095686e6fcb4150f0a55b1a25987fad3d8af58d6 ]
Add a consistency check for L2's guest_ia32_debugctl, as KVM only supports a subset of hardware functionality, i.e. KVM can't rely on hardware to detect illegal/unsupported values. Failure to check the vmcs12 value would allow the guest to load any harware-supported value while running L2.
Take care to exempt BTF and LBR from the validity check in order to match KVM's behavior for writes via WRMSR, but without clobbering vmcs12. Even if VM_EXIT_SAVE_DEBUG_CONTROLS is set in vmcs12, L1 can reasonably expect that vmcs12->guest_ia32_debugctl will not be modified if writes to the MSR are being intercepted.
Arguably, KVM _should_ update vmcs12 if VM_EXIT_SAVE_DEBUG_CONTROLS is set *and* writes to MSR_IA32_DEBUGCTLMSR are not being intercepted by L1, but that would incur non-trivial complexity and wouldn't change the fact that KVM's handling of DEBUGCTL is blatantly broken. I.e. the extra complexity is not worth carrying.
Cc: stable@vger.kernel.org Signed-off-by: Maxim Levitsky mlevitsk@redhat.com Co-developed-by: Sean Christopherson seanjc@google.com Link: https://lore.kernel.org/r/20250610232010.162191-7-seanjc@google.com Signed-off-by: Sean Christopherson seanjc@google.com Stable-dep-of: 7d0cce6cbe71 ("KVM: VMX: Wrap all accesses to IA32_DEBUGCTL with getter/setter APIs") Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/vmx/nested.c | 12 ++++++++++-- arch/x86/kvm/vmx/vmx.c | 5 ++--- arch/x86/kvm/vmx/vmx.h | 3 +++ 3 files changed, 15 insertions(+), 5 deletions(-)
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index d3e346a574f1..c626be098fde 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2564,7 +2564,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (vmx->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) { kvm_set_dr(vcpu, 7, vmcs12->guest_dr7); - vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl); + vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl & + vmx_get_supported_debugctl(vcpu, false)); } else { kvm_set_dr(vcpu, 7, vcpu->arch.dr7); vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.pre_vmenter_debugctl); @@ -3045,7 +3046,8 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, return -EINVAL;
if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) && - CC(!kvm_dr7_valid(vmcs12->guest_dr7))) + (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) || + CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false)))) return -EINVAL;
if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) && @@ -4435,6 +4437,12 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) (vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) | (vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE);
+ /* + * Note! Save DR7, but intentionally don't grab DEBUGCTL from vmcs02. + * Writes to DEBUGCTL that aren't intercepted by L1 are immediately + * propagated to vmcs12 (see vmx_set_msr()), as the value loaded into + * vmcs02 doesn't strictly track vmcs12. + */ if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) kvm_get_dr(vcpu, 7, (unsigned long *)&vmcs12->guest_dr7);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 48a72ad8a28f..65a1ab742c89 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2153,7 +2153,7 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu, return (unsigned long)data; }
-static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated) +u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated) { u64 debugctl = 0;
@@ -2168,8 +2168,7 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated return debugctl; }
-static bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, - bool host_initiated) +bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated) { u64 invalid;
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 6be1627d888e..e61442db7cbb 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -432,6 +432,9 @@ static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr,
void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu);
+u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated); +bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated); + /* * Note, early Intel manuals have the write-low and read-high bitmap offsets * the wrong way round. The bitmaps control MSRs 0x00000000-0x00001fff and
On Thu, Aug 14, 2025, Sasha Levin wrote:
From: Maxim Levitsky mlevitsk@redhat.com
[ Upstream commit 095686e6fcb4150f0a55b1a25987fad3d8af58d6 ]
Add a consistency check for L2's guest_ia32_debugctl, as KVM only supports a subset of hardware functionality, i.e. KVM can't rely on hardware to detect illegal/unsupported values. Failure to check the vmcs12 value would allow the guest to load any harware-supported value while running L2.
Take care to exempt BTF and LBR from the validity check in order to match KVM's behavior for writes via WRMSR, but without clobbering vmcs12. Even if VM_EXIT_SAVE_DEBUG_CONTROLS is set in vmcs12, L1 can reasonably expect that vmcs12->guest_ia32_debugctl will not be modified if writes to the MSR are being intercepted.
Arguably, KVM _should_ update vmcs12 if VM_EXIT_SAVE_DEBUG_CONTROLS is set *and* writes to MSR_IA32_DEBUGCTLMSR are not being intercepted by L1, but that would incur non-trivial complexity and wouldn't change the fact that KVM's handling of DEBUGCTL is blatantly broken. I.e. the extra complexity is not worth carrying.
Cc: stable@vger.kernel.org Signed-off-by: Maxim Levitsky mlevitsk@redhat.com Co-developed-by: Sean Christopherson seanjc@google.com Link: https://lore.kernel.org/r/20250610232010.162191-7-seanjc@google.com Signed-off-by: Sean Christopherson seanjc@google.com Stable-dep-of: 7d0cce6cbe71 ("KVM: VMX: Wrap all accesses to IA32_DEBUGCTL with getter/setter APIs") Signed-off-by: Sasha Levin sashal@kernel.org
Acked-by: Sean Christopherson seanjc@google.com
Once again with the caveat that this lands after the RTM_DEBUG patch (which I also acked).
https://lore.kernel.org/all/20250813183728.2070321-1-sashal@kernel.org
From: Maxim Levitsky mlevitsk@redhat.com
[ Upstream commit 7d0cce6cbe71af6e9c1831bff101a2b9c249c4a2 ]
Introduce vmx_guest_debugctl_{read,write}() to handle all accesses to vmcs.GUEST_IA32_DEBUGCTL. This will allow stuffing FREEZE_IN_SMM into GUEST_IA32_DEBUGCTL based on the host setting without bleeding the state into the guest, and without needing to copy+paste the FREEZE_IN_SMM logic into every patch that accesses GUEST_IA32_DEBUGCTL.
No functional change intended.
Cc: stable@vger.kernel.org Signed-off-by: Maxim Levitsky mlevitsk@redhat.com [sean: massage changelog, make inline, use in all prepare_vmcs02() cases] Reviewed-by: Dapeng Mi dapeng1.mi@linux.intel.com Link: https://lore.kernel.org/r/20250610232010.162191-8-seanjc@google.com Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/vmx/nested.c | 10 +++++----- arch/x86/kvm/vmx/pmu_intel.c | 8 ++++---- arch/x86/kvm/vmx/vmx.c | 8 +++++--- arch/x86/kvm/vmx/vmx.h | 10 ++++++++++ 4 files changed, 24 insertions(+), 12 deletions(-)
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index c626be098fde..b453c72cb4c7 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2564,11 +2564,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (vmx->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) { kvm_set_dr(vcpu, 7, vmcs12->guest_dr7); - vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl & - vmx_get_supported_debugctl(vcpu, false)); + vmx_guest_debugctl_write(vcpu, vmcs12->guest_ia32_debugctl & + vmx_get_supported_debugctl(vcpu, false)); } else { kvm_set_dr(vcpu, 7, vcpu->arch.dr7); - vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.pre_vmenter_debugctl); + vmx_guest_debugctl_write(vcpu, vmx->nested.pre_vmenter_debugctl); } if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) @@ -3433,7 +3433,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
if (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) - vmx->nested.pre_vmenter_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); + vmx->nested.pre_vmenter_debugctl = vmx_guest_debugctl_read(); if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) @@ -4633,7 +4633,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, __vmx_set_segment(vcpu, &seg, VCPU_SREG_LDTR);
kvm_set_dr(vcpu, 7, 0x400); - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); + vmx_guest_debugctl_write(vcpu, 0);
if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr, vmcs12->vm_exit_msr_load_count)) diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 48a2f77f62ef..50364e00e4e9 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -633,11 +633,11 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu) */ static void intel_pmu_legacy_freezing_lbrs_on_pmi(struct kvm_vcpu *vcpu) { - u64 data = vmcs_read64(GUEST_IA32_DEBUGCTL); + u64 data = vmx_guest_debugctl_read();
if (data & DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) { data &= ~DEBUGCTLMSR_LBR; - vmcs_write64(GUEST_IA32_DEBUGCTL, data); + vmx_guest_debugctl_write(vcpu, data); } }
@@ -707,7 +707,7 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu)
if (!lbr_desc->event) { vmx_disable_lbr_msrs_passthrough(vcpu); - if (vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR) + if (vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR) goto warn; if (test_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use)) goto warn; @@ -729,7 +729,7 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu)
static void intel_pmu_cleanup(struct kvm_vcpu *vcpu) { - if (!(vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR)) + if (!(vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR)) intel_pmu_release_guest_lbr_event(vcpu); }
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 65a1ab742c89..89f6e56fa5fe 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2128,7 +2128,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vmx->pt_desc.guest.addr_a[index / 2]; break; case MSR_IA32_DEBUGCTLMSR: - msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL); + msr_info->data = vmx_guest_debugctl_read(); break; default: find_uret_msr: @@ -2258,7 +2258,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) VM_EXIT_SAVE_DEBUG_CONTROLS) get_vmcs12(vcpu)->guest_ia32_debugctl = data;
- vmcs_write64(GUEST_IA32_DEBUGCTL, data); + vmx_guest_debugctl_write(vcpu, data); + if (intel_pmu_lbr_is_enabled(vcpu) && !to_vmx(vcpu)->lbr_desc.event && (data & DEBUGCTLMSR_LBR)) intel_pmu_create_guest_lbr_event(vcpu); @@ -4826,7 +4827,8 @@ static void init_vmcs(struct vcpu_vmx *vmx) vmcs_write32(GUEST_SYSENTER_CS, 0); vmcs_writel(GUEST_SYSENTER_ESP, 0); vmcs_writel(GUEST_SYSENTER_EIP, 0); - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); + + vmx_guest_debugctl_write(&vmx->vcpu, 0);
if (cpu_has_vmx_tpr_shadow()) { vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index e61442db7cbb..ede940c48c6e 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -435,6 +435,16 @@ void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu); u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated); bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated);
+static inline void vmx_guest_debugctl_write(struct kvm_vcpu *vcpu, u64 val) +{ + vmcs_write64(GUEST_IA32_DEBUGCTL, val); +} + +static inline u64 vmx_guest_debugctl_read(void) +{ + return vmcs_read64(GUEST_IA32_DEBUGCTL); +} + /* * Note, early Intel manuals have the write-low and read-high bitmap offsets * the wrong way round. The bitmaps control MSRs 0x00000000-0x00001fff and
On Thu, Aug 14, 2025, Sasha Levin wrote:
From: Maxim Levitsky mlevitsk@redhat.com
[ Upstream commit 7d0cce6cbe71af6e9c1831bff101a2b9c249c4a2 ]
Introduce vmx_guest_debugctl_{read,write}() to handle all accesses to vmcs.GUEST_IA32_DEBUGCTL. This will allow stuffing FREEZE_IN_SMM into GUEST_IA32_DEBUGCTL based on the host setting without bleeding the state into the guest, and without needing to copy+paste the FREEZE_IN_SMM logic into every patch that accesses GUEST_IA32_DEBUGCTL.
No functional change intended.
Cc: stable@vger.kernel.org Signed-off-by: Maxim Levitsky mlevitsk@redhat.com [sean: massage changelog, make inline, use in all prepare_vmcs02() cases] Reviewed-by: Dapeng Mi dapeng1.mi@linux.intel.com Link: https://lore.kernel.org/r/20250610232010.162191-8-seanjc@google.com Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Sasha Levin sashal@kernel.org
Acked-by: Sean Christopherson seanjc@google.com
On Thu, Aug 14, 2025, Sasha Levin wrote:
From: Sean Christopherson seanjc@google.com
[ Upstream commit 8a4351ac302cd8c19729ba2636acfd0467c22ae8 ]
Move VMX's logic to check DEBUGCTL values into a standalone helper so that the code can be used by nested VM-Enter to apply the same logic to the value being loaded from vmcs12.
KVM needs to explicitly check vmcs12->guest_ia32_debugctl on nested VM-Enter, as hardware may support features that KVM does not, i.e. relying on hardware to detect invalid guest state will result in false negatives. Unfortunately, that means applying KVM's funky suppression of BTF and LBR to vmcs12 so as not to break existing guests.
No functional change intended.
Reviewed-by: Dapeng Mi dapeng1.mi@linux.intel.com Link: https://lore.kernel.org/r/20250610232010.162191-6-seanjc@google.com Signed-off-by: Sean Christopherson seanjc@google.com Stable-dep-of: 7d0cce6cbe71 ("KVM: VMX: Wrap all accesses to IA32_DEBUGCTL with getter/setter APIs") Signed-off-by: Sasha Levin sashal@kernel.org
Acked-by: Sean Christopherson seanjc@google.com
linux-stable-mirror@lists.linaro.org
-
gregkh＠linuxfoundation.org -
Sasha Levin -
Sean Christopherson